GENERALIZABLE FEATURES FROM U NSUPERVISED LEARNING

Humans learn a predictive model of the world and use this model to reason about future events and the consequences of actions. In contrast to most machine predictors, we exhibit an impressive ability to generalize to unseen scenarios and reason intelligently in these settings. One important aspect of this ability is physical intuition (Lake et al., 2016). In this work, we explore the potential of unsupervised learning to find features that promote better generalization to settings outside the supervised training distribution. Our task is predicting the stability of towers of square blocks. We demonstrate that an unsupervised model, trained to predict future frames of a video sequence of stable and unstable block configurations, can yield features that support extrapolating stability prediction to blocks configurations outside the training set distribution.

[1]  Yann LeCun,et al.  Deep multi-scale video prediction beyond mean square error , 2015, ICLR.

[2]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[4]  Jitendra Malik,et al.  Learning Visual Predictive Models of Physics for Playing Billiards , 2015, ICLR.

[5]  Lucas Theis,et al.  Amortised MAP Inference for Image Super-resolution , 2016, ICLR.

[6]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

[7]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[8]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[9]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[10]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[11]  Joshua B. Tenenbaum,et al.  Building machines that learn and think like people , 2016, Behavioral and Brain Sciences.

[12]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[13]  Nitish Srivastava,et al.  Unsupervised Learning of Video Representations using LSTMs , 2015, ICML.

[14]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[15]  Sergey Levine,et al.  Deep visual foresight for planning robot motion , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[16]  Vysoké Učení,et al.  Statistical Language Models Based on Neural Networks , 2012 .

[17]  Jiajun Wu,et al.  A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding , 2016, CogSci.

[18]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[19]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[20]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[21]  Gabriel Kreiman,et al.  Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning , 2016, ICLR.

[22]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[23]  Rob Fergus,et al.  Learning Physical Intuition of Block Towers by Example , 2016, ICML.

[24]  J. Stockman.  Pure Reasoning in 12-Month-Old Infants as Probabilistic Inference , 2013 .

[25]  Honglak Lee,et al.  Action-Conditional Video Prediction using Deep Networks in Atari Games , 2015, NIPS.

[26]  Sergey Levine,et al.  Unsupervised Learning for Physical Interaction through Video Prediction , 2016, NIPS.

[27]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.